DeepRacer on Physical Track: Parameters Exploration and Performance Evaluation

TL;DR

This study evaluates hyperparameter effects and object avoidance capabilities of AWS DeepRacer on a physical track, highlighting differences from simulated environments and identifying ongoing challenges.

Contribution

It systematically explores hyperparameter impacts and assesses object avoidance transfer from simulation to real-world settings for DeepRacer.

Findings

Higher gradient descent batch size improves performance in simulation.

Huber loss outperforms MSE in both environments.

Object avoidance is effective in simulation but challenging physically.

Abstract

This paper focuses on the physical racetrack capabilities of AWS DeepRacer. Two separate experiments were conducted. The first experiment (Experiment I) focused on evaluating the impact of hyperparameters on the physical environment. Hyperparameters such as gradient descent batch size and loss type were changed systematically as well as training time settings. The second experiment (Experiment II) focused on exploring AWS DeepRacer object avoidance in the physical environment. It was uncovered that in the simulated environment, models with a higher gradient descent batch size had better performance than models with a lower gradient descent batch size. Alternatively, in the physical environment, a gradient descent batch size of 128 appears to be preferable. It was found that models using the loss type of Huber outperformed models that used the loss type of MSE in both the simulated and physical environments. Finally, object avoidance in the simulated environment appeared to be effective; however, when bringing these models to the physical environment, there was a pronounced challenge to avoid objects. Therefore, object avoidance in the physical environment remains an open challenge.